{
  "annotation_id": "33c2966b-e8ff-4eeb-971b-0f80a66eaf58",
  "date_created": "2026-02-17T05:53:24.052000Z",
  "date_modified": "2026-02-17T05:53:24.052000Z",
  "file_hash": "dd8311b39b12a09c91f762036e75eb6b1da17bafe9c3f29bd8269f2b8b005361",
  "private": false,
  "record": {
    "abstract": "This paper introduces a novel Multi-Agent Cooperative Learning (MACL) framework to address cross-modal alignment collapse in vision-language models when handling out-of-distribution (OOD) concepts. Four core agents, including image, text, name, and coordination agents, collaboratively mitigate modality imbalance through structured message passing. The proposed framework enables multi-agent feature space name learning, incorporates a context exchange enhanced few-shot learning algorithm, and adopts an adaptive dynamic balancing mechanism to regulate inter-agent contributions. Experiments on the VISTA-Beyond dataset demonstrate that MACL significantly improves performance in both few-shot and zero-shot settings, achieving 1-5% precision gains across diverse visual domains.",
    "arxiv_id": "2601.09746",
    "authors": [
      "Philip Xu",
      "Isabel Wagner",
      "Eerke Boiten"
    ],
    "categories": [
      "cs.MA",
      "cs.AI",
      "cs.CV",
      "cs.LG"
    ],
    "license": "http://creativecommons.org/licenses/by/4.0/",
    "title": "Multi-Agent Cooperative Learning for Robust Vision-Language Alignment under OOD Concepts",
    "url": "https://arxiv.org/abs/2601.09746",
    "version": "v1"
  },
  "schema_id": "dorsal/arxiv",
  "source": {
    "execution_id": "9236e2d7-6acf-4708-b5a8-9bac875e7502",
    "id": "arXiv Dataset",
    "type": "Model",
    "variant": "snapshot-2026-01-17",
    "version": "0.1.0"
  },
  "user_id": 1000002
}